GitHub - clintmckenna/polymarketR: R Interface to Polymarket Prediction Markets
R Interface to Polymarket Prediction Markets. Contribute to clintmckenna/polymarketR development by creating an account on GitHub.
For anyone interested in working with Polymarket data, I put together a simple R package to query event and market prices and other information. Very much a WIP, so feel free to give any feedback or suggestions! #rstats
github.com/clintmckenna...
15.07.2025 21:28 — 👍 2 🔁 1 💬 1 📌 0
GitHub - clintmckenna/oTree_gpt: Collection of oTree app templates for running experiments with LLM agents.
Collection of oTree app templates for running experiments with LLM agents. - clintmckenna/oTree_gpt
For any researchers interested in embedding AI agents in behavioral experiments, here is my code and a video tutorial walkthrough!
Code: github.com/clintmckenna...
Video: www.youtube.com/watch?v=IY_U...
Feel free to get in touch if I can help your research! clint@calsocial.org
23.02.2025 17:47 — 👍 1 🔁 0 💬 0 📌 0
Gif animation of a behavioral experiment using threejs platform to show how participants can chat with agents in a 3D space and have distinct conversations triggered by physical distance.
Animation of a chat with an LLM agent triggered by participant's voice, which is transcribed, sent to the server, and replied back via a virtual text-to-speech service.
Animation of a dictator game experiment where the LLM agent's perception of the participant programmatically affects a trust rating score.
How can researchers effectively and ethically use LLM agents in social experiments? I had the pleasure of discussing this topic with some wonderful researchers at my roundtable session at #SPSP2025
Here are some resources below! ⬇️
23.02.2025 17:45 — 👍 5 🔁 3 💬 1 📌 0
The results from a data sample of 192 human participants. Democrat participants were more likely to choose to read articles shared by Democrat politicians than Republican politicians. Conversely, Republican participants were more likely to choose to read articles shared by Republican politicians than Democrat politicians.
For each of the 9 models tested, this shows a figure similar to that of the human participants. In all cases, the models exaggerate the political selective exposure bias far beyond what you expect to see from a similar sample of human participants.
If you asked an LLM agent to act as a Republican or Democrat, how biased would you expect them to be? In a selective exposure task, simulated participants seem to exaggerate their political bias relative to what you would see in a human sample.
calsocial.org/research/202...
#ai #llm #socialscience
17.01.2025 00:39 — 👍 0 🔁 1 💬 1 📌 0
A comprehensive thread on our recent paper. If you are interested in motivated reasoning and expertise, please take a look!
21.12.2024 21:48 — 👍 1 🔁 0 💬 0 📌 0
